World models
World models are neural networks that learn an internal representation of an environment’s dynamics, enabling agents to simulate and plan within a learned latent space. They are used in model-based reinforcement learning, robotics, and autonomous decision-making.
- GitHub: https://github.com/topics/world-models
- Last updated: 2026-03-13 00:28:32 UTC
- JSON Representation
https://github.com/danijar/dreamerv3
Mastering Diverse Domains through World Models
artificial-intelligence general jax minecraft reinforcement-learning world-models
Last synced: 14 May 2025
https://github.com/eloialonso/diamond
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
artificial-intelligence atari deep-learning diffusion-models machine-learning reinforcement-learning research world-models
Last synced: 26 Feb 2025
https://github.com/danijar/dreamerv2
Mastering Atari with Discrete World Models
artificial-intelligence atari deep-learning machine-learning reinforcement-learning research robotics video-prediction world-models
Last synced: 08 Apr 2025
https://github.com/nvidia-cosmos/cosmos-predict2.5
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
foundational-models video-generation world-models
Last synced: 24 Feb 2026
https://github.com/eloialonso/iris
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
artificial-intelligence atari deep-learning machine-learning reinforcement-learning research transformers world-models
Last synced: 27 Apr 2025
https://github.com/opendrivelab/driveagi
[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving & Foundation Models in Autonomous System
autonomous-driving embodied-ai foundation-model general-artificial-intelligence large-dataset policy-learning video-dataset video-generation world-models
Last synced: 15 May 2025
https://github.com/danijar/dreamer
Dream to Control: Learning Behaviors by Latent Imagination
artificial-intelligence deep-learning reinforcement-learning robotics world-models
Last synced: 05 Apr 2025
https://github.com/thu-ml/Causal-Forcing
Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"
auto-regressive-diffusion-model autoregressive-models consistency-models diffusion diffusion-models distillation few-step-generation generative-ai text-to-video text-to-video-generation video-diffusion-model video-generation wan-video wan2 wan21 world-model world-models
Last synced: 05 Mar 2026
https://github.com/danijar/daydreamer
DayDreamer: World Models for Physical Robot Learning
reinforcement-learning robotics world-models
Last synced: 09 Apr 2025
https://github.com/zhanghm1995/Forge_VFM4AD
A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.
3dgs adaptation autonomous-driving diffusion end-to-end-autonomous-driving foundation-model large-language-models nerf pre-training survey world-models
Last synced: 24 Jul 2025
https://github.com/lucidrains/genie2-pytorch
Implementation of a framework for Genie2 in Pytorch
artificial-intelligence attention deep-learning transformers world-models
Last synced: 12 Apr 2025
https://github.com/YvanYin/DrivingWorld
Code for "DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT"
autonomous-driving driving-world-model generative-model gpt video-generation video-gpt world-models
Last synced: 12 Oct 2025
https://github.com/dweam-team/world-arcade
Find and Play Generative Games Locally
ai-games diffusion-models emulator games video-game video-models world-models
Last synced: 06 Apr 2025
https://github.com/danijar/director
Deep Hierarchical Planning from Pixels
algorithms decision-making deep-learning hierarchical-reinforcement-learning planning reinforcement-learning sparse-rewards world-models
Last synced: 12 Apr 2025
https://github.com/Kevin-thu/Epona
Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)
autonomous-driving diffusion-models video-generation world-models
Last synced: 28 Jan 2026
https://github.com/minnie-lin/Awesome-Physics-Cognition-based-Video-Generation
A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.
3d 4d embodied-ai physics survey t2v v2v video-generation world-models world-simulator
Last synced: 16 Apr 2025
https://github.com/opendrivelab/nexus
Nexus: Decoupled Diffusion Sparks Adaptive Scene Generation
diffusion-models scene-generation world-models
Last synced: 10 Jun 2025
https://github.com/thuml/harmonydream
Code release for "HarmonyDream: Task Harmonization Inside World Models" (ICML 2024), https://arxiv.org/abs/2310.00344
model-based-reinforcement-learning world-models
Last synced: 25 Jul 2025
https://github.com/juliuskunze/cwvae-jax
Clockwork VAEs in JAX/Flax
deep-learning jax machine-learning research video-prediction world-models
Last synced: 15 Jul 2025
https://github.com/princeton-nlp/lwm
We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effectively control these agents through verbal communication.
Last synced: 23 Apr 2025
https://github.com/lukehollis/agentics-3d
Create multi-agent simulations in game engines for realistic human behaviors and synthetic training data
civilization machine-learning npc reinforcement-learning unity world-models
Last synced: 22 Apr 2025
https://github.com/charmve/gpt-eyes
I GAVE GPT-4 EYES!
agent gpt-4 gpt-4o gpt-4omni gpt4 gpt4v llm llm-inference world-model world-models worldmodel
Last synced: 14 Oct 2025
https://github.com/arnaudvl/world-models-ppo
PyTorch World Model implementation with PPO.
mdrnn pytorch reinforcement-learning vae world-models
Last synced: 14 Apr 2025
https://github.com/voidful/mmlm
Toward Multi Modality Language Model - implementation of GPT-4o/Project Astra
gpt-4o multi-modality multi-model world-models
Last synced: 04 Sep 2025
https://github.com/itomasaki/pixyzrl
A Bayesian RL Framework with Probabilistic Generative Models
ai artificial-intelligence baysian-inference deep-learning machine-learning nueral-network pixyz python reinforcement-learning rl robotics world-models
Last synced: 10 Oct 2025
https://github.com/nik-55/world-models
A curated list of research and projects on world models
curated-list physical-ai spatial-intelligence world-models
Last synced: 27 Feb 2026
https://github.com/lukehollis/llm-urban-simulations
Unity-based character AI system using ML-Agents and world models for realistic NPC behaviors and decision-making
civilization machine-learning npc reinforcement-learning unity world-models
Last synced: 08 Oct 2025
https://github.com/nima-siboni/narrow-corridor-ai
A reinforcement learning project for crowd-dynamics in a very narrow corridor
dynamic-programming multi-agent-reinforcement-learning policy-evaluation policy-iteration world-models
Last synced: 08 Oct 2025
https://github.com/brunoocs/world-model-2018
Modern PyTorch implementation of World Models with interactive notebooks for the Car Racing environment. Features VAE vision model, MDN-RNN memory system, and CMA-ES controller with visualization tools. Complete end-to-end reinforcement learning pipeline with clean, well-documented code.
cma-es mdn pytorch rnn world-models
Last synced: 06 May 2025
https://github.com/walidght/deep-hierarchical-planning
PyTorch reimplementation of "Deep Hierarchical Planning" RL framework. Features a multi-model architecture with manager-worker policies, world model, and goal autoencoder. Built with Python/PyTorch and includes experiment logging with Weights & Biases.
deeplearning goal-autoencoder hierarchical-rl machine-learning manager-worker neurips-2022 python pytorch reinforcement-learning research-paper rl-framework world-models
Last synced: 19 Oct 2025
https://github.com/jorahn/jorahn
Profile for Jonathan Rahn — AI Lab Lead at Drees & Sommer. Chess-reasoning LMs (policy + world model), RL with verifiable rewards.
chess-ai cot policy rlvr self-play transformers trl world-models
Last synced: 19 Sep 2025
